BlockchainAnalysis

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Beyond the readOnlyHint annotation, the description adds meaningful behavioral details: it reads the issuer's blacklist directly across 15 chains, reports prior-freeze signals, and explicitly declares that it reports observed facts only, not causes. The 'Free' note also discloses cost, showing strong transparency.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is efficient and front-loaded with the core purpose. The chain list, while long, is useful for quick reference, and each sentence adds value (purpose, behavior, output caveat). It is slightly longer than a minimal two-sentence description but not bloated.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description sufficiently explains what the tool returns: a frozen/not frozen on-chain fact and a prior-freeze signal. It also clarifies what it does NOT return (cause of freeze), making the tool's behavior complete for a simple check tool despite lacking explicit output structure.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% for both parameters (address and chain), with the chain enum fully listed and address format explained. The description adds no new parameter semantics beyond reinforcing that the check spans multiple chains, so it stays at the baseline for well-covered schemas.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: checking whether USDT or USDC have blacklisted (frozen) a wallet address on-chain. It specifies the resource (issuer's blacklist function), the action (read/check), and the scope (15 named chains), which distinguishes it from sibling tools like get_freeze_events or kyt_risk.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides clear context for when to use this tool—when you need to know if a wallet is frozen on-chain for USDT/USDC. It also states what it does NOT do ('never the cause of a freeze'), which implicitly guides users to other tools for cause analysis, though it does not explicitly name alternatives.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Beyond the readOnlyHint annotation, the description adds substantial context: risk scoring against entity labels, flagging unlimited allowances and stale grants, and the 'read-only' nature is reinforced. It discloses exactly what the tool evaluates and the source of risk data, providing strong behavioral transparency.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two concise sentences that front-load the core purpose and then add valuable detail (risk labels, flags). Every phrase earns its place with no redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description compensates by indicating what the user gets: a list of approvals, risk scores, and flags. It also states scope limitations ('Ethereum only') and cost ('Free'), making it self-contained for a simple single-parameter tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema already covers the parameter fully (wallet address pattern and 'Ethereum only' instruction). The description adds no additional meaning about the parameter, so it meets the baseline expected for 100% schema coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb and resource: 'List a wallet's active ERC-20 token approvals on Ethereum and who can move its funds.' It immediately differentiates from siblings like check_token_security or check_stablecoin_freeze by focusing specifically on approvals and risk scoring.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Clear context is provided: 'Ethereum only' and 'Read-only' plus the intended use case 'The wallet's attack surface at a glance.' However, it does not explicitly mention when not to use this tool or name alternative tools, so it stops short of a 5.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description goes beyond annotations by stating 'No transaction is sent' and 'Reports observed facts... not verdicts', which are important behavioral traits. It also mentions the cross-referencing against BA's entity labels, adding transparency about the underlying data. No contradiction with readOnlyHint.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is three sentences, front-loaded with purpose, then lists detection capabilities, reporting style, supported chains, safety, and cost. Every sentence adds value with no redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description gives a hint about outputs ('observed facts') but does not detail response structure. It covers supported chains and the tool's non-transactional nature, making it fairly complete for a two-parameter security scan tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with descriptions for both token and chain, including an enum for chain. The description adds context about ERC-20 and DEX simulation but does not provide additional parameter-specific semantics beyond what a high-coverage schema already offers.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states it simulates buy-and-sell transactions to surface honeypots, extreme transfer taxes, name/symbol impersonation, and active mint authority. This specific verb+resource scope distinguishes it from sibling tools like check_stablecoin_freeze and check_token_approvals.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It provides clear context for usage: security scanning of ERC-20 tokens on supported chains, with no transaction sent and free. However, it does not explicitly name alternatives or state when not to use this tool, though the purpose is implied.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Beyond the readOnlyHint and openWorldHint annotations, the description discloses the data sources (issuers' on-chain blacklist events across multiple chains), the limitation that each row never states the cause, and that the tool is free. These are meaningful behavioral traits that aid the agent in understanding what to expect.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is well-structured and front-loaded: it starts with the core purpose, then filters, then the critical sibling distinction, then a caveat, and finally cost. Each of the five sentences earns its place without redundant filler, making it appropriately sized for the tool's complexity.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the well-documented schema and strong annotations, the description covers all essential context: what the tool does, the data provenance, how to filter, when to use an alternative, a key limitation, and cost. It is complete enough for an agent to select and invoke the tool correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema already covers 100% of parameter semantics, so the baseline is 3. The description adds a general 'omit all filters for recent events' note, but does not enrich individual parameter meanings beyond what the schema provides.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool queries the stablecoin freeze ledger, specifically the history of freeze/unfreeze/destroy events. It names the issuers and chains, and explicitly distinguishes itself from check_stablecoin_freeze by noting it is event history, not current status.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives explicit guidance on when to use this tool vs alternatives: it says to use check_stablecoin_freeze for current freeze status, and describes how to filter by address, chain, kind, or time, including the hint to omit all filters for recent events. It also cautions that the history never states the cause, which helps set expectations.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true, and the description adds significant context beyond that: it discloses the tool is paid per call via x402 (USDC), the coverage limitation (31 chains with entity-label data vs the rest sanctions/freeze-only), and that the response itself indicates the coverage mode. No contradiction with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three sentences, front-loaded with the core purpose, then components, coverage caveat, and cost. No fluff; each sentence adds distinct information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a two-parameter read-only tool, the description covers what it does, the verdict output, limitations, and cost. It doesn't fully specify the response structure, but the absence of an output schema is mitigated by describing the verdict levels and flags. Overall, an agent has enough to invoke it correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema descriptions fully cover both parameters, so baseline is 3. The description adds value by telling the agent which chains (54) are supported and that on 31 of them the verdict is backed by entity-label data, enabling chain-specific expectations. It also implies the address must match the chain format, consistent with schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb 'Assess' and resource 'wallet's KYT risk', then details the components (sanctions screening, BA entity classification, VASP/jurisdiction risk score, cluster context) and the output verdict levels. It distinguishes itself from 'a raw label list' and sibling tools like screen_address by emphasizing behavioral risk aggregation.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It doesn't name alternative tools, but provides clear context: this is a wallet-level behavioral risk verdict, not a label list, and notes data coverage differences across chains. The mention of being 'distinct from a raw label list' and the chain-specific backing caveat help an agent decide when this tool is appropriate, though explicit exclusions are absent.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Beyond the annotations (readOnly, openWorld), the description adds substantial behavioral detail: it screens both sides, returns a combined verdict and recommendation, has directional flags, covers 54 chains with varying data backing, and is paid per call. It also discloses that the response will indicate when only sanctions/freeze screening applies, which is important for interpreting results.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is moderately long but structured: purpose first, then scope, then output, then limitations, then payment. Each clause provides distinctive information without redundancy. It is front-loaded with the main action and readable, though it packs many details into one sentence.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Since there is no output schema, the description sufficiently explains what the tool returns: verdict, recommendation, directional flags, and chain-specific caveats. It also covers data coverage, limitations, and pricing, leaving few ambiguities for an agent deciding to invoke it.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema already fully documents from/to/chain (100% coverage). The description adds semantic clarity by explaining that both 'from' and 'to' are screened, and that the output is transaction-level. It also implies that the chain parameter influences data quality. This goes beyond the bare schema definitions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's function: 'Assess the KYT risk of a transaction between two wallets'. It specifies the resource (transaction) and the action (assess), and differentiates from the sibling tool kyt_risk by calling this the 'transaction analogue'. It also lists concrete outputs (verdict, recommendation, directional flags).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides context by clarifying this is for transaction-level screening of both sender and recipient, and notes coverage of 54 chains with data-quality caveats. It explicitly names kyt_risk as an analogue, giving an alternative reference. However, it does not explicitly state 'when not to use' or mention how it differs from other siblings like screen_address.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint true; description adds that it shows free vs paid calls and includes the 'Free' note, enriching the cost/behavior context without contradicting annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two concise sentences plus a one-word 'Free.' convey purpose, usage, and cost without redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a parameterless discovery tool with read-only annotations, the description fully covers purpose, usage timing, content, and pricing, leaving no significant gaps.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

No parameters exist, so schema coverage is complete. The description correctly implies no arguments are needed, and no further param semantics are required.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool lists the BlockchainAnalysis MCP tools, supported chains, and pricing. It distinguishes itself from sibling analysis tools by positioning as a discovery entry point.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly instructs to call this first before invoking other tools, providing clear when-to-use guidance and setting expectations for discovery.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Beyond the readOnlyHint and openWorldHint annotations, the description discloses that the tool is 'Paid per call via x402 (USDC)'—important behavioral context. It also explains the derivation from 'BA sanctions + entity labels,' giving transparency on the data source. The description adds value without contradicting annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is three sentences, with the main purpose front-loaded, differentiation in the second sentence, and supported chains plus pricing in the third. No filler or redundant content. Every sentence adds distinct value.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool has no output schema, the description compensates by explaining the return format (verdict, 0-100 score, confidence tier, plain-language reasons). It also covers supported chains, cost, and relationship to sibling tools. For a 2-parameter read-only tool, this is complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema already provides 100% coverage for both parameters (address and chain) with clear descriptions. The tool description does not add new parameter-specific meaning beyond what the schema states. Per the rubric, a baseline of 3 is appropriate when schema coverage is high.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose with a specific verb and resource: 'Get a consumer-protection verdict for a wallet or contract.' It also explicitly distinguishes itself from sibling tools by naming 'screen_address' for raw labels and 'kyt_risk' for transactional risk. The output format (verdict, score, confidence tier, reasons) is explained.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly answers the usage question ('Answers "is it safe to interact with this address?"') and provides direct alternative guidance by saying 'Distinct from raw labels (screen_address) and transactional risk (kyt_risk).' This tells the agent when to use this tool and when not to. Supported chains are listed, and cost/payment method is noted.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint and openWorldHint, so the safety profile is covered. The description adds valuable behavioral context: it is 'Paid per call via x402 (USDC)', which is a critical cost implication, and it specifies that each label carries threat level, source, and confidence. It also clarifies cross-chain support (EVM, TRON, SOL, BTC), going beyond the bare schema. No contradiction with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is three sentences, each earning its place: first states the core purpose and label types, second explains the label structure (threat level, source, confidence), and third covers chain scope and pricing. No filler or redundancy. It front-loads the main action and uses a clear, scannable format.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with only 2 parameters and no output schema, this description is remarkably complete. It explains what the tool does, the format of the returned labels (threat level, source, confidence), supported chains, and payment method. There is no ambiguity about input or output expectations, making the tool usable without additional documentation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema fully documents both parameters (address and chain). The description adds minimal meaning beyond the schema: it mentions supported chains but the schema already lists them. It implicitly relates 'address' to 'wallet' but does not provide additional syntax, format, or edge-case guidance. Thus, baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb 'Screen' and the resource 'a wallet against BlockchainAnalysis's 1B+ entity-label dataset'. It enumerates specific label categories (sanctions, scam, phishing, exploit, mixer, exchange) and the return value ('raw labels'). This distinguishes it from sibling tools like kyt_risk/kyt_tx that likely focus on transactions rather than address-level screening.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no explicit guidance on when to use this tool versus alternatives such as kyt_risk or other sibling tools. It does not mention exclusions, prerequisites, or a recommended context beyond the tool's general purpose. Usage is implied but not explicitly differentiated, so the agent must infer from the description alone.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.